Sparse 3D convolutional neural networks

Ben Graham

Abstract

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition and analysis of space-time objects. In the quest for efficiency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.

Session

Poster 2

Files

PDF iconExtended Abstract (PDF, 1339K)
PDF iconPaper (PDF, 1496K)

DOI

10.5244/C.29.150
https://dx.doi.org/10.5244/C.29.150

Citation

Ben Graham. Sparse 3D convolutional neural networks. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 150.1-150.9. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_150,
	title={Sparse 3D convolutional neural networks},
	author={Ben Graham},
	year={2015},
	month={September},
	pages={150.1-150.9},
	articleno={150},
	numpages={9},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.150},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.150}
}